urban/data_mining_algorithms
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

kmeans Minor Bugfixes

Browse Source 
- Added cluster to test generator
- Added sample data to main
This commit is contained in:
Conrad
2018-06-02 23:30:07 +02:00
parent 7ea392c302
commit 4e3ceac4a9
4 changed files with 62 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/algorithms/dmlib.py
View File

@@ -1,5 +1,5 @@
# Calculate the difference between two points giving the indexes of these data entries
def calcdiff(point1, point2, data):
def calcdiff(point1, point2):
if int(point2) > int(point1):
difference = int(point2) - int(point1)
else:
@@ -19,4 +19,22 @@ def findHighest(data):
for i in range(0, len(data)):
if int(data[i]) > maximum:
maximum = int(data[i])
return maximum
return maximum
def pp_calcdiff(data, clusterpoint):
max_diff = 0
new_cluster = 0
for item in range(0,len(data)):
if calcdiff(data[item], clusterpoint) > max_diff:
max_diff = calcdiff(data[item], clusterpoint)
new_cluster = data[item]
return new_cluster
def pp_calcdiff_2(data, clusterpoint, clusterpoint_2):
max_diff = 0
new_cluster = 0
for item in range(0,len(data)):
if calcdiff(data[item], clusterpoint) + calcdiff(data[item], clusterpoint_2) > max_diff:
max_diff = calcdiff(data[item], clusterpoint)
new_cluster = data[item]
return new_cluster

4
src/algorithms/dmtest.py
View File

@@ -8,8 +8,10 @@ def plzGen(entries):
for i in range(0, int(entries)):
if i < round(entries * 0.4):
plz = generateNumber(plz_lenght, 2)
elif i >= round(entries * 0.4) and i < round(entries * 0.8):
elif i >= round(entries * 0.4) and i < round(entries * 0.6):
plz = generateNumber(plz_lenght, 9)
elif i >= round(entries * 0.6) and i < round(entries * 0.9):
plz = generateNumber(plz_lenght, 4)
else:
plz = generateNumber(plz_lenght, randint(0,9))
dataArray.append(plz)

6
src/algorithms/kmeansMkI.py
View File

@@ -107,8 +107,8 @@ def assignCluster(data, highPoint, clusters):
# Check the difference between the point (item) and each cluster and set min_cluster to the smallest difference
for cluster in range(0, clusters):
if min_cluster > dmlib.calcdiff(data[item], globals()["cpoint_" + str(cluster)], new_data[0]):
min_cluster = dmlib.calcdiff(data[item], globals()["cpoint_" + str(cluster)], new_data[0])
if min_cluster > dmlib.calcdiff(data[item], globals()["cpoint_" + str(cluster)]):
min_cluster = dmlib.calcdiff(data[item], globals()["cpoint_" + str(cluster)])
assinged_cluster = globals()["cpoint_" + str(cluster)]
# Assign the minimal difference cluster to the data
data_assigned.append(assinged_cluster)
@@ -135,6 +135,6 @@ def startup(data):
print(str(seconds) + " seconds for execution")
# Start the algorithm and generate test data
data = dmtest.plzGen(1000)
data = dmtest.plzGen(10000)
startup(data)